Tile2Vec: Unsupervised Representation Learning for Spatially Distributed Data

Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we introduce Tile2Vec, an unsupervised representation learning algorithm that extends the distributional hypothesis from natural language — words appearing in similar contexts tend to have similar meanings — to spatially distributed data. We demonstrate empirically that Tile2Vec learns semantically meaningful representations for both image and non-image datasets. Our learned representations significantly improve performance in downstream classification tasks and, similarly to word vectors, allow visual analogies to be obtained via simple arithmetic in the latent space.

Authors

• Neal Jean
• Sherrie Wang Massachusetts Institute of Technology, Cambridge, MA, USA
• Anshul Samar
• George Azzari
• David Lobell Stanford University
• Stefano Ermon Stanford University

Keywords

No keywords are indexed for this paper.